Related papers: Neural translation for Stokes inversion and synthe…
The development of robust and generalisable models for encoding the spatio-temporal dynamics of human brain activity is crucial for advancing neuroscientific discoveries. However, significant individual variation in the organisation of the…
We aim at demonstrating the capabilities of a newly developed method for determining electric currents in the solar photosphere. We employ three-dimensional radiative magneto-hydrodynamic (MHD) simulations to produce synthetic Stokes…
Steady-state solutions to the Navier-Stokes equations are known to admit solutions that are singular at the sonic point. Consequently, inviscid solar wind models require special treatment of the solution near the sonic points, and this has…
Sea surface temperature (SST) is an essential climate variable that can be measured via ground truth, remote sensing, or hybrid model methodologies. Here, we celebrate SST surveillance progress via the application of a few relevant…
High-resolution images of the solar surface show a granulation pattern of hot rising and cooler downward-sinking material -- the top of the deep-reaching solar convection zone. Convection plays a role for the thermal structure of the solar…
We examine whether or not it is possible to derive the field strength distribution of quiet Sun internetwork regions from very high spatial resolution polarimetric observations in the visible. In particular, we consider the case of the…
Deep state-space models (DSSMs) enable temporal predictions by learning the underlying dynamics of observed sequence data. They are often trained by maximising the evidence lower bound. However, as we show, this does not ensure the model…
We introduce Seed-to-Seed Translation (StS), a novel approach for Image-to-Image Translation using diffusion models (DMs), aimed at translations that require close adherence to the structure of the source image. In contrast to existing…
Climate simulations are essential in guiding our understanding of climate change and responding to its effects. However, it is computationally expensive to resolve complex climate processes at high spatial resolution. As one way to speed up…
A fast and spectrally accurate Ewald summation method for the evaluation of stokeslet, stresslet and rotlet potentials of three-dimensional Stokes flow is presented. This work extends the previously developed Spectral Ewald method for…
A central challenge in climate science and applied mathematics is developing data-driven models of multiscale systems that capture both stationary statistics and responses to external perturbations. Current neural climate emulators aim to…
Deep generative models have been enjoying success in modeling continuous data. However it remains challenging to capture the representations for discrete structures with formal grammars and semantics, e.g., computer programs and molecular…
Scheduled sampling is an effective method to alleviate the exposure bias problem of neural machine translation. It simulates the inference scene by randomly replacing ground-truth target input tokens with predicted ones during training.…
Downscaling aims to link the behaviour of the atmosphere at fine scales to properties measurable at coarser scales, and has the potential to provide high resolution information at a lower computational and storage cost than numerical…
Given an image dataset, we are often interested in finding data generative factors that encode semantic content independently from pose variables such as rotation and translation. However, current disentanglement approaches do not impose…
When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems…
Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce. But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or Machine Translation (MT)…
High-stakes applications require AI-generated models to be interpretable. Current algorithms for the synthesis of potentially interpretable models rely on objectives or regularization terms that represent interpretability only coarsely…
Inverse problems in fluid dynamics are ubiquitous in science and engineering, with applications ranging from electronic cooling system design to ocean modeling. We propose a general and robust approach for solving inverse problems in the…
We explore how neural differential equations (NDEs) may be trained on highly resolved fluid-dynamical models of unresolved scales providing an ideal framework for data-driven parameterizations in climate models. NDEs overcome some of the…